Implementing an q-learning agent to solve the "Hunt the Wumpus" game getting the best reward using the reinforcement learning technique.
To run the code you have to create an anaconda environment with the configuration file found in environment.yml and then activate it to run the code. The required commands to make it work are the following:
- conda create env -f environment.yml
- jupyter lab
Contributors: Artem Merinov & Rigels Hita